INDEX

Explanations

words that express subjective opinions or judgements

oai_token-act-pair · gemini-2.0-flash

character traits

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.63

 disambiguazione

-0.60

EnableWeb

-0.54

lunda

-0.52

loadAll

-0.52

Obr

-0.51

MathML

-0.51

 intptr

-0.50

erring

-0.49

الإنجليزية

-0.49

POSITIVE LOGITS

 }}$}

0.47

}*/

0.45

хьтан

0.45

VIAF

0.45

ladin

0.44

！）

0.44

SPATH

0.43

 Roskov

0.43

ificent

0.43

ümüş

0.43

Activations Density 16.766%

words that express subjective opinions or judgements

character traits

No Comments

No Known Activations

words that express subjective opinions or judgements

character traits

No Comments

No Known Activations